This implementation highly based on official code yao8839836/text_gcn.
- Python 3.6
- PyTorch 1.0
cd ./preprocess
- Run
python remove_words.py <dataset>
- Run
python build_graph.py <dataset>
cd ..
- Run
python train.py <dataset>
- Replace
<dataset>
with20ng
,R8
,R52
,ohsumed
ormr
Pre-tained model placed in ‘model_save’.
This work was supported by the National Key R&D Program of China under Grant No. 2020AAA0103804(Sponsor: Hefu Liu). This work belongs to the University of science and technology of China.